© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 13314
    Prev
    Next
    INDEX
    Explanations

    proper nouns matching "Mann"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Mann" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emir
    -0.75
    GGGGGGGG
    -0.69
    ffic
    -0.63
    EEEE
    -0.63
     Dangerous
    -0.62
    CLUS
    -0.61
    dfx
    -0.60
    actly
    -0.60
     Absent
    -0.59
     CLS
    -0.59
    POSITIVE LOGITS
    ucci
    1.03
    olini
    1.01
    heim
    1.01
    agher
    0.98
    ificent
    0.93
    heimer
    0.92
    fred
    0.92
    ifest
    0.91
    arian
    0.88
    elli
    0.88
    Activations Density 0.011%

    No Known Activations